> For the complete documentation index, see [llms.txt](https://docs.cherryai.com.cn/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cherryai.com.cn/advanced-basic/extensions.md).

# 扩展 Agent 的能力

技能、MCP 与能力边界

Agent 已经带有文件、搜索、图片、记忆、工作流、定时任务等内置工具。需要固定工作方法时添加技能，需要连接外部系统时添加 MCP。两者解决的问题不同，不必为了“功能更多”全部安装。

<figure><img src="https://3562065924-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F0Ut5BptC3t8CtSU1UWpM%2Fuploads%2FIdUbdTffaPFsqQbMbg05%2Fclipboard.png?alt=media&amp;token=bccbea1c-dfcd-402c-b418-bd3b419e6516" alt="根据资料、固定方法和外部系统需求选择内置工具、知识库、技能或 MCP 的关系图"><figcaption><p>优先使用最短路径；只有 Agent 确实需要访问外部系统时才增加 MCP。</p></figcaption></figure>

## 先判断需要什么

| 需求                | 选择         |
| ----------------- | ---------- |
| 固定一套步骤、模板或检查清单    | 技能         |
| 查询数据库、浏览器或第三方系统   | MCP        |
| 检索自己的文档资料         | 知识库        |
| 读写当前项目文件、生成图片或发通知 | Agent 内置工具 |

{% hint style="success" %}
最方便的做法是直接在【工作】中描述目标，让 Agent 帮你判断缺少的是技能、MCP 还是知识库。需要核对来源、连接参数或权限时，再到【设置】手动管理。
{% endhint %}

## 安装后的最后一步

全局安装或连接成功，不代表每个 Agent 都能使用。打开【工作】→ Agent 菜单→【编辑】，分别在【技能】、【MCP】或【知识库】中选择。配置从下一条消息开始生效。

<figure><img src="https://3562065924-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F0Ut5BptC3t8CtSU1UWpM%2Fuploads%2F8jBsu2mUDHVw67Q8pLBL%2Fclipboard.png?alt=media&amp;token=9a56b427-0884-4a60-8c62-a9fc15e5d9f7" alt="Agent 编辑窗口中的内置工具、知识库、MCP 和技能入口"><figcaption><p>Agent 的内置工具、知识库、MCP 和技能分别配置，按任务需要启用。</p></figcaption></figure>

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>技能与能力库</strong></td><td>安装并复用稳定工作方法</td><td><a href="/advanced-basic/extensions/skills.md">技能与能力库</a></td></tr><tr><td><strong>MCP 与外部工具</strong></td><td>连接额外工具和数据来源</td><td><a href="/advanced-basic/extensions/mcp.md">MCP 与外部工具</a></td></tr><tr><td><strong>MCP 排错</strong></td><td>按连接链路逐步定位问题</td><td><a href="/advanced-basic/extensions/mcp/troubleshooting.md">MCP 排错</a></td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.cherryai.com.cn/advanced-basic/extensions.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
